C14 - Semiparametric and Nonparametric Methods: GeneralReturn

The urgent need to address climate change and the depletion of natural resources has led governments worldwide to allocate significant resources towards research and development in clean energy technologies and energy efficiency. This study evaluates the effectiveness of renewable energy and energy efficiency initiatives in reducing CO₂ emissions, taking into account the influences of natural resource availability and political risk. Using data from France spanning from 1985 to 2021, we employ the kernel-based regularized least squares (KRLS) methodology, complemented by quantile regression (QR), to analyse these relationships. Our findings indicate that policies promoting energy efficiency and green energy have a positive impact on reducing CO₂ emissions. However, the availability of natural resources and political risk exacerbate environmental challenges by increasing CO₂ emissions. Thus, our study underscores the importance of continued support from policymakers for renewable energy development and energy efficiency research to effectively pursue Sustainable Development Goals (SDGs). Additionally, as the world prepares for COP28, our findings emphasize the urgency of these initiatives in meeting global climate targets.

The aim of the paper is to identify differences in innovation efficiency of national innovation systems of Slovakia and selected countries of the European Union (Austria, Belgium, Bulgaria, the Czech Republic, Estonia, Germany, Romania and Sweden) in the period 2006-2015. The relative efficiency model applied uses a non-parametric method known as data envelopment analysis (DEA) in a super-efficiency version with a constant-returns-to-scale technology and input orientation. The data selection is based on innovation indicators and methodological aspects of the model. The authors discovered that Austria and Germany achieved an efficient score for technological efficiency, Belgium, Estonia, Romania and Slovakia for economic efficiency, and only Austria for overall efficiency. The research identifies peers for Slovakia among all the EU countries at all levels of efficiency, provides several recommendations for improvement and also confirms the existence of small countries' resulting bias.

The paper deals with the examining the possibilities for diagnosing the corporate financial health using Data Envelopment Analysis (DEA) technique. The main aim of the paper is to present a new proposal for diagnosing the corporate financial health by DEA, to predict financial distress of Slovak manufacturing companies using the proposed procedure, and to assess the potential of DEA as a tool for predicting financial distress of the company. Due to the special input and output variables selection and the construction of the Corporate Distress Frontier, the proposed procedure is very different from the conventional use of DEA. The proposed two-step procedure results into the identification of three zones of corporate financial health with different stage of corporate distress risk. The application of the proposed procedure to Slovak manufacturing companies and its comparison with the logistic regression model and decision tree show relatively satisfactory results of the proposed methodology in terms of correct classification of non-bankrupt firms.

We study the effects of corruption on firm efficiency using a unique comprehensive dataset of private firms from 10 Central and Eastern European countries for the period from 2002 to 2013. We find that an environment characterized by a high level of corruption has an adverse effect on firm efficiency. This effect is amplified for firms with a lower propensity to behave corruptly, i.e. foreign-controlled firms, while domestically-owned firms are not penalized. At the same time, an environment characterized by considerable heterogeneity in perception of corruption is associated with an increase in firm efficiency.

Cluster Analysis of Jumps on Capital Markets We analyze the behavior and performance of multiple price jump indicators across capital markets and over time. By using high-frequency we perform cluster analysis of price jump indicators that share similar properties in terms of their performance in that they minimize Type I and Type II errors. We show that clusters of price jump indicators do not exhibit equal size. Clusters are stable across stock market indices and time. Detected numbers of price jumps are also stable over time. The recent financial crisis does not seem to affect the overall jumpiness of mature or emerging stock markets. Our results support the stress testing approach of the Basel III. Accords in that the jump component of the volatility process does not need to be treated separately for the purpose of stress testing.

Our study investigates the benefits that the Czech inhabitants could gain from the reduction of road traffic noise. We applied contingent valuation study in order to estimate willingness-to-pay (WTP) for the reduction of traffic noise by 10 dB (from 70 dB up 60 dB). Using data from 2010 Czech representative survey (n=2,104), we estimated mean WTP by nonparametric method which was based on the Kaplan-Meier estimate. Further, we explained the variability of WTP using Double-Hurdle model. In the first step, the Probit model explained the choice of individuals that are willing to participate on the program decreasing the road noise. In the second step, the log-normal regression model explained the variability of WTP on the socio-economic characteristics of individuals and characteristics of noise in the area where people live.

The models from the GARCH family are often estimated by maximum likelihood method, either parametrically or non-parametrically. Since the parametric estimation procedure is based on an a priori distribution, its misspecification can lead to the inconsistency of the estimators. Therefore non-parametric approach, in which both model's parameters and the distribution of error terms are estimated from the data, seems to be a better alternative. In our work, we propose a non-parametric technique with the use of a heuristic called differential evolution to estimate the parameters of a GARCH-M model. This technique can more likely reach to a global solution of maximum likelihood estimation (MLE) task. Further, it can also more effectively control the required properties of the estimates. The suitability of our approach is verified on modeling the CZK/USD and CZK/EURO forward exchange rate premium of period from 2007 to 2012 by a GARCH-M model.

In various fields of macroeconomic modelling, researchers often face the problem of decomposing time series into trend component and cycle fluctuations. While there are several potentially useful methods to perform the task in question, Hodrick-Prescott (HP) fi lter seems to have remained (despite some serious criticism) the most popular approach over the past decade. In this article I propose a straightforward and easy-to-implement bootstrap procedure for building pointwise and simultaneous confidence intervals around "point estimates" produced by HP filter. The principle of proposed method can be described as follows: first, we use maximum entropy bootstrap (Vinod, 2004, 2006) to approximate ensemble from which original time series is drawn and then apply the HP filter directly to each bootstrap replication. If necessary, the proposed method can be adapted to allow for uncertainty in the smoothing parameter. Practical usefulness of our approach is demonstrated with an application to the GDP data. Results are encouraging - obtained confi dence intervals for the trend and cyclical component are overall plausible thus supplying a researcher with some measure of uncertainty related to HP filtering. Finally, we demonstrate that a former approach to build confidence intervals for HP filter (Gallego and Johnson, 2005) leads to erratic inference for cycle due to the shape-destroying block bootstrap sampling.

Learning is a subject of intense research in economics. We present persuasive evidence that learning took place among uninformed heterogeneous agents during a large-scale naturally-occurring set of auctions. Empirical study employs a unique bidding data set of 5000 individual investors that placed their bids in the voucher scheme that in terms of size, incentives, and variation is one of the largest experiments ever conducted. To detect and quantify learning we develop new measures of individual performance during the bidding process on the artificial stock market where prices of goods vary over successive stages of bidding on the basis of supply and demand.